Text recognition method and device and storage medium thereof

A text recognition and text technology, which is applied in character and pattern recognition, text database clustering/classification, unstructured text data retrieval, etc. It can solve the problems of low accuracy of relation classification, low efficiency of relation extraction and limited effect of entity relation extraction. , to achieve the effect of reducing workload, improving accuracy and efficiency

Inactive Publication Date: 2019-03-08
CHENGDU SEFON SOFTWARE CO LTD
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current relationship extraction methods have limited effect on entity relationship extraction, and the

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Text recognition method and device and storage medium thereof
  • Text recognition method and device and storage medium thereof
  • Text recognition method and device and storage medium thereof

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0027] According to the applicant's research, it is found that the existing methods for extracting entity relations from texts are generally rule-based extraction methods or machine learning-based statistical learning methods. The rule-based relationship extraction method is to manually write rules to identify the relationship between two entities in a sentence or discourse; the relationship extraction method based on machine statistical learning usually converts the relationship extraction problem into a classification problem. Among the current relationship extraction methods, the rule-based method has obvious shortcomings. This method needs to manually write a large number of rules, the workload is very large, it is not easy to maintain, and the rules must be written for each field, which cannot be well extended to other fields. ; Based on the method of unsupervised learning, when clustering sentences or discourses, the effect is often not very good, and a lot of manual inte...

no. 2 example

[0061] In order to cooperate with the text recognition method provided in the first embodiment of the present invention, the second embodiment of the present invention further provides a text recognition device 100 .

[0062] Please refer to image 3 , image 3 It is a block diagram of a text recognition device provided by the second embodiment of the present invention.

[0063] The text recognition device 100 includes an acquisition module 110 and an entity relationship determination module 120 .

[0064] An acquisition module 110, configured to acquire text to be processed.

[0065] The entity relationship determination module 120 is configured to input the text to be processed into a text recognition model based on convolutional neural network and attention mechanism, and obtain the entity relationship of the text to be processed output by the text recognition model.

[0066] As an optional implementation manner, the text recognition device 100 in this embodiment may als...

no. 3 example

[0073] Please refer to Figure 4 , Figure 4 The third embodiment of the present invention provides a structural block diagram of an electronic device applicable to the embodiments of the present application. The electronic device 200 provided in this embodiment may include a text recognition apparatus 100 , a memory 201 , a storage controller 202 , a processor 203 , a peripheral interface 204 , an input / output unit 205 , an audio unit 206 , and a display unit 207 .

[0074] The memory 201, storage controller 202, processor 203, peripheral interface 204, input and output unit 205, audio unit 206, and display unit 207 are electrically connected to each other directly or indirectly to realize data transmission or interact. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The text recognition device 100 includes at least one software function module that can be stored in the memory 201 in the for...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a text recognition method and device and a storage medium thereof, which relate to the technical field of relation extraction and classification. The text recognition method comprises the following steps of obtaining the text to be processed; inputting the text to be processed into a text recognition model based on a convolution neural network and an attention mechanism, andobtaining the entity relationship of the text to be processed outputted from the text recognition model. This text recognition method improves the accuracy of relation classification and has higher efficiency of relation extraction by extracting the entity relation of text based on the convolution neural network and attention mechanism of text recognition model.

Description

technical field [0001] The present invention relates to the technical field of relation extraction and classification thereof, in particular to a text recognition method, device and storage medium thereof. Background technique [0002] Nowadays, the Internet has become the main channel for people to obtain information, and the content of text data on the Internet is also showing an exponential growth trend. Text data on the Internet is very useful for us to build knowledge bases or knowledge graphs; however, the workload of manual knowledge extraction is extremely huge. If computers can understand and extract useful information, it will be of great significance. However, almost all text data on the Internet exists in the form of natural language, which is unstructured and cannot be directly processed by computers. In order to solve this problem, information extraction technology emerges as the times require. Information extraction technology extracts structured data from un...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F16/35G06F16/36G06F17/27G06K9/62G06N3/04
CPCG06F40/284G06N3/045G06F18/2411
Inventor 覃进学王纯斌赵神州蓝科
Owner CHENGDU SEFON SOFTWARE CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap